Research

20 pages, 22507 KiB

Open AccessArticle

Real-Time Dense Semantic Labeling with Dual-Path Framework for High-Resolution Remote Sensing Image

by Yuhao Wang, Chen Chen, Meng Ding and Jiangyun Li

Remote Sens. 2019, 11(24), 3020; https://doi.org/10.3390/rs11243020 - 14 Dec 2019

Cited by 15 | Viewed by 2950

Dense semantic labeling plays a pivotal role in high-resolution remote sensing image research. It provides pixel-level classification which is crucial in land cover mapping and urban planning. With the recent success of the convolutional neural network (CNN), accuracy has been greatly improved by [...] Read more.

Dense semantic labeling plays a pivotal role in high-resolution remote sensing image research. It provides pixel-level classification which is crucial in land cover mapping and urban planning. With the recent success of the convolutional neural network (CNN), accuracy has been greatly improved by previous works. However, most networks boost performance by involving too many parameters and computational overheads, which results in more inference time and hardware resources, while some attempts with light-weight networks do not achieve satisfactory results due to the insufficient feature extraction ability. In this work, we propose an efficient light-weight CNN based on dual-path architecture to address this issue. Our model utilizes three convolution layers as the spatial path to enhance the extraction of spatial information. Meanwhile, we develop the context path with the multi-fiber network (MFNet) followed by the pyramid pooling module (PPM) to obtain a sufficient receptive field. On top of these two paths, we adopt the channel attention block to refine the features from the context path and apply a feature fusion module to combine spatial information with context information. Moreover, a weighted cascade loss function is employed to enhance the learning procedure. With all these components, the performance can be significantly improved. Experiments on the Potsdam and Vaihingen datasets demonstrate that our network performs better than other light-weight networks, even some classic networks. Compared to the state-of-the-art U-Net, our model achieves higher accuracy on the two datasets with 2.5 times less network parameters and 22 times less computational floating point operations (FLOPs). Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

18 pages, 26932 KiB

Open AccessArticle

by Bo Peng, Zonglin Meng, Qunying Huang and Caixia Wang

Remote Sens. 2019, 11(21), 2492; https://doi.org/10.3390/rs11212492 - 24 Oct 2019

Cited by 43 | Viewed by 4749

Abstract

Urban flooding is a major natural disaster that poses a serious threat to the urban environment. It is highly demanded that the flood extent can be mapped in near real-time for disaster rescue and relief missions, reconstruction efforts, and financial loss evaluation. Many [...] Read more.

Urban flooding is a major natural disaster that poses a serious threat to the urban environment. It is highly demanded that the flood extent can be mapped in near real-time for disaster rescue and relief missions, reconstruction efforts, and financial loss evaluation. Many efforts have been taken to identify the flooding zones with remote sensing data and image processing techniques. Unfortunately, the near real-time production of accurate flood maps over impacted urban areas has not been well investigated due to three major issues. (1) Satellite imagery with high spatial resolution over urban areas usually has nonhomogeneous background due to different types of objects such as buildings, moving vehicles, and road networks. As such, classical machine learning approaches hardly can model the spatial relationship between sample pixels in the flooding area. (2) Handcrafted features associated with the data are usually required as input for conventional flood mapping models, which may not be able to fully utilize the underlying patterns of a large number of available data. (3) High-resolution optical imagery often has varied pixel digital numbers (DNs) for the same ground objects as a result of highly inconsistent illumination conditions during a flood. Accordingly, traditional methods of flood mapping have major limitations in generalization based on testing data. To address the aforementioned issues in urban flood mapping, we developed a patch similarity convolutional neural network (PSNet) using satellite multispectral surface reflectance imagery before and after flooding with a spatial resolution of 3 meters. We used spectral reflectance instead of raw pixel DNs so that the influence of inconsistent illumination caused by varied weather conditions at the time of data collection can be greatly reduced. Such consistent spectral reflectance data also enhance the generalization capability of the proposed model. Experiments on the high resolution imagery before and after the urban flooding events (i.e., the 2017 Hurricane Harvey and the 2018 Hurricane Florence) showed that the developed PSNet can produce urban flood maps with consistently high precision, recall, F1 score, and overall accuracy compared with baseline classification models including support vector machine, decision tree, random forest, and AdaBoost, which were often poor in either precision or recall. The study paves the way to fuse bi-temporal remote sensing images for near real-time precision damage mapping associated with other types of natural hazards (e.g., wildfires and earthquakes). Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

21 pages, 2021 KiB

Open AccessArticle

Multi-Channel Weather Radar Echo Extrapolation with Convolutional Recurrent Neural Networks

by Quang-Khai Tran and Sa-kwang Song

Remote Sens. 2019, 11(19), 2303; https://doi.org/10.3390/rs11192303 - 02 Oct 2019

Cited by 37 | Viewed by 5202

Abstract

This article presents an investigation into the problem of 3D radar echo extrapolation in precipitation nowcasting, using recent AI advances, together with a viewpoint from Computer Vision. While Deep Learning methods, especially convolutional recurrent neural networks, have been developed to perform extrapolation, most [...] Read more.

This article presents an investigation into the problem of 3D radar echo extrapolation in precipitation nowcasting, using recent AI advances, together with a viewpoint from Computer Vision. While Deep Learning methods, especially convolutional recurrent neural networks, have been developed to perform extrapolation, most works use 2D radar images rather than 3D images. In addition, the very few ones which try 3D data do not show a clear picture of results. Through this study, we found a potential problem in the convolution-based prediction of 3D data, which is similar to the cross-talk effect in multi-channel radar processing but has not been documented well in the literature, and discovered the root cause. The problem was that, when we generated different channels using one receptive field, some information in a channel, especially observation errors, might affect other channels unexpectedly. We found that, when using the early-stopping technique to avoid over-fitting, the receptive field did not learn enough to cancel unnecessary information. If we increased the number of training iterations, this effect could be reduced but that might worsen the over-fitting situation. We therefore proposed a new output generation block which generates each channel separately and showed the improvement. Moreover, we also found that common image augmentation techniques in Computer Vision can be helpful for radar echo extrapolation, improving testing mean squared error of employed models at least 20% in our experiments. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Figure 1

23 pages, 3045 KiB

Open AccessArticle

Deep Learning for Soil and Crop Segmentation from Remotely Sensed Data

by Jack Dyson, Adriano Mancini, Emanuele Frontoni and Primo Zingaretti

Remote Sens. 2019, 11(16), 1859; https://doi.org/10.3390/rs11161859 - 09 Aug 2019

Cited by 46 | Viewed by 7375

Abstract

One of the most challenging problems in precision agriculture is to correctly identify and separate crops from the soil. Current precision farming algorithms based on artificially intelligent networks use multi-spectral or hyper-spectral data to derive radiometric indices that guide the operational management of [...] Read more.

One of the most challenging problems in precision agriculture is to correctly identify and separate crops from the soil. Current precision farming algorithms based on artificially intelligent networks use multi-spectral or hyper-spectral data to derive radiometric indices that guide the operational management of agricultural complexes. Deep learning applications using these big data require sensitive filtering of raw data to effectively drive their hidden layer neural network architectures. Threshold techniques based on the normalized difference vegetation index (NDVI) or other similar metrics are generally used to simplify the development and training of deep learning neural networks. They have the advantage of being natural transformations of hyper-spectral or multi-spectral images that filter the data stream into a neural network, while reducing training requirements and increasing system classification performance. In this paper, to calculate a detailed crop/soil segmentation based on high resolution Digital Surface Model (DSM) data, we propose the redefinition of the radiometric index using a directional mathematical filter. To further refine the analysis, we feed this new radiometric index image of about 3500 × 4500 pixels into a relatively small Convolution Neural Network (CNN) designed for general image pattern recognition at 28 × 28 pixels to evaluate and resolve the vegetation correctly. We show that the result of applying a DSM filter to the NDVI radiometric index before feeding it into a Convolutional Neural Network can potentially improve crop separation hit rate by 65%. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

22 pages, 3100 KiB

Open AccessArticle

SmokeNet: Satellite Smoke Scene Detection Using Convolutional Neural Network with Spatial and Channel-Wise Attention

by Rui Ba, Chen Chen, Jing Yuan, Weiguo Song and Siuming Lo

Remote Sens. 2019, 11(14), 1702; https://doi.org/10.3390/rs11141702 - 18 Jul 2019

Cited by 87 | Viewed by 10256

Abstract

A variety of environmental analysis applications have been advanced by the use of satellite remote sensing. Smoke detection based on satellite imagery is imperative for wildfire detection and monitoring. However, the commonly used smoke detection methods mainly focus on smoke discrimination from a [...] Read more.

A variety of environmental analysis applications have been advanced by the use of satellite remote sensing. Smoke detection based on satellite imagery is imperative for wildfire detection and monitoring. However, the commonly used smoke detection methods mainly focus on smoke discrimination from a few specific classes, which reduces their applicability in different regions of various classes. To this end, in this paper, we present a new large-scale satellite imagery smoke detection benchmark based on Moderate Resolution Imaging Spectroradiometer (MODIS) data, namely USTC_SmokeRS, consisting of 6225 satellite images from six classes (i.e., cloud, dust, haze, land, seaside, and smoke) and covering various areas/regions over the world. To build a baseline for smoke detection in satellite imagery, we evaluate several state-of-the-art deep learning-based image classification models. Moreover, we propose a new convolution neural network (CNN) model, SmokeNet, which incorporates spatial and channel-wise attention in CNN to enhance feature representation for scene classification. The experimental results of our method using different proportions (16%, 32%, 48%, and 64%) of training images reveal that our model outperforms other approaches with higher accuracy and Kappa coefficient. Specifically, the proposed SmokeNet model trained with 64% training images achieves the best accuracy of 92.75% and Kappa coefficient of 0.9130. The model trained with 16% training images can also improve the classification accuracy and Kappa coefficient by at least 4.99% and 0.06, respectively, over the state-of-the-art models. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

19 pages, 4549 KiB

Open AccessArticle

Unsupervised Feature-Learning for Hyperspectral Data with Autoencoders

by Lloyd Windrim, Rishi Ramakrishnan, Arman Melkumyan, Richard J. Murphy and Anna Chlingaryan

Remote Sens. 2019, 11(7), 864; https://doi.org/10.3390/rs11070864 - 10 Apr 2019

Cited by 32 | Viewed by 10215

Abstract

This paper proposes novel autoencoders for unsupervised feature-learning from hyperspectral data. Hyperspectral data typically have many dimensions and a significant amount of variability such that many data points are required to represent the distribution of the data. This poses challenges for higher-level algorithms [...] Read more.

This paper proposes novel autoencoders for unsupervised feature-learning from hyperspectral data. Hyperspectral data typically have many dimensions and a significant amount of variability such that many data points are required to represent the distribution of the data. This poses challenges for higher-level algorithms which use the hyperspectral data (e.g., those that map the environment). Feature-learning mitigates this by projecting the data into a lower-dimensional space where the important information is either preserved or enhanced. In many applications, the amount of labelled hyperspectral data that can be acquired is limited. Hence, there is a need for feature-learning algorithms to be unsupervised. This work proposes unsupervised techniques that incorporate spectral measures from the remote-sensing literature into the objective functions of autoencoder feature learners. The proposed techniques are evaluated on the separability of their feature spaces as well as on their application as features for a clustering task, where they are compared against other unsupervised feature-learning approaches on several different datasets. The results show that autoencoders using spectral measures outperform those using the standard squared-error objective function for unsupervised hyperspectral feature-learning. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

29 pages, 11609 KiB

Open AccessArticle

Automated Mapping of Woody Debris over Harvested Forest Plantations Using UAVs, High-Resolution Imagery, and Machine Learning

by Lloyd Windrim, Mitch Bryson, Michael McLean, Jeremy Randle and Christine Stone

Remote Sens. 2019, 11(6), 733; https://doi.org/10.3390/rs11060733 - 26 Mar 2019

Cited by 28 | Viewed by 5237

Abstract

Surveying of woody debris left over from harvesting operations on managed forests is an important step in monitoring site quality, managing the extraction of residues and reconciling differences in pre-harvest inventories and actual timber yields. Traditional methods for post-harvest survey involving manual assessment [...] Read more.

Surveying of woody debris left over from harvesting operations on managed forests is an important step in monitoring site quality, managing the extraction of residues and reconciling differences in pre-harvest inventories and actual timber yields. Traditional methods for post-harvest survey involving manual assessment of debris on the ground over small sample plots are labor-intensive, time-consuming, and do not scale well to heterogeneous landscapes. In this paper, we propose and evaluate new automated methods for the collection and interpretation of high-resolution, Unmanned Aerial Vehicle (UAV)-borne imagery over post-harvested forests for estimating quantities of fine and coarse woody debris. Using high-resolution, geo-registered color mosaics generated from UAV-borne images, we develop manual and automated processing methods for detecting, segmenting and counting both fine and coarse woody debris, including tree stumps, exploiting state-of-the-art machine learning and image processing techniques. Results are presented using imagery over a post-harvested compartment in a Pinus radiata plantation and demonstrate the capacity for both manual image annotations and automated image processing to accurately detect and quantify coarse woody debris and stumps left over after harvest, providing a cost-effective and scalable survey method for forest managers. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

12 pages, 2642 KiB

Open AccessArticle

Sparse Cost Volume for Efficient Stereo Matching

by Chuanhua Lu, Hideaki Uchiyama, Diego Thomas, Atsushi Shimada and Rin-ichiro Taniguchi

Remote Sens. 2018, 10(11), 1844; https://doi.org/10.3390/rs10111844 - 20 Nov 2018

Cited by 29 | Viewed by 5359

Abstract

Stereo matching has been solved as a supervised learning task with convolutional neural network (CNN). However, CNN based approaches basically require huge memory use. In addition, it is still challenging to find correct correspondences between images at ill-posed dim and sensor noise regions. [...] Read more.

Stereo matching has been solved as a supervised learning task with convolutional neural network (CNN). However, CNN based approaches basically require huge memory use. In addition, it is still challenging to find correct correspondences between images at ill-posed dim and sensor noise regions. To solve these problems, we propose Sparse Cost Volume Net (SCV-Net) achieving high accuracy, low memory cost and fast computation. The idea of the cost volume for stereo matching was initially proposed in GC-Net. In our work, by making the cost volume compact and proposing an efficient similarity evaluation for the volume, we achieved faster stereo matching while improving the accuracy. Moreover, we propose to use weight normalization instead of commonly-used batch normalization for stereo matching tasks. This improves the robustness to not only sensor noises in images but also batch size in the training process. We evaluated our proposed network on the Scene Flow and KITTI 2015 datasets, its performance overall surpasses the GC-Net. Comparing with the GC-Net, our SCV-Net achieved to: (1) reduce

73.08 %

GPU memory cost; (2) reduce

61.11 %

processing time; (3) improve the 3PE from

2.87 %

to

2.61 %

on the KITTI 2015 dataset. Full article

(This article belongs to the Special Issue Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Joint Artificial Intelligence and Computer Vision Applications in Remote Sensing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI